From bba4658dd34114fcc0e997dd35e8a5b53a014781 Mon Sep 17 00:00:00 2001
From: prlanzarin <4529051+prlanzarin@users.noreply.github.com>
Date: Tue, 15 Aug 2023 22:03:09 -0300
Subject: [PATCH] fix(recording): remux bbb-webrtc-recorder and KMS files
 during archive

Kurento may *rarely* generate WebM/MKV files with corrupt or absent
SeekHead sectors. bbb-webrtc-recorder also doesn't generate SeekHead or
even the Cues sectors by default.

While those are are *optional* fields by spec, files need to be seekable
for our recording processing scripts to work.

This commit adds a remuxing step for Kurento and bbb-webrtc-recorder raw
files that is executed during the archive phase. It should re-include
any of the missing fields that make files seekable and restore the Cues
sector in WebM files.
---
 .../core/scripts/archive/archive.rb           | 39 +++++++++++++++++--
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/record-and-playback/core/scripts/archive/archive.rb b/record-and-playback/core/scripts/archive/archive.rb
index 6f0283c38e..0074f1c64c 100755
--- a/record-and-playback/core/scripts/archive/archive.rb
+++ b/record-and-playback/core/scripts/archive/archive.rb
@@ -111,6 +111,37 @@ def delete_audio(meeting_id, audio_dir)
   end
 end
 
+def remux_and_archive(source_dir, dest_dir)
+  files = Dir.glob("#{source_dir}/*")
+
+  if files.empty?
+    BigBlueButton.logger.warn("No media files found in #{source_dir}")
+    return
+  end
+
+  BigBlueButton.logger.info("Remuxing and archiving files at #{source_dir}")
+  FileUtils.mkdir_p(dest_dir)
+
+  files .each do |file|
+    ext = File.extname(file)
+    next if ext.empty?
+    # These can potentially be webm (VP8/VP9), mp4 (H.264), or mkv (VP8/VP9/H.264)
+    output_basename = File.join(dest_dir, File.basename(file, ext))
+    format = {
+      extension: ext.delete_prefix('.'),
+      parameters: [
+        %w[-c copy],
+      ]
+    }
+    BigBlueButton::EDL.encode(
+      nil,
+      file,
+      format,
+      output_basename
+    )
+  end
+end
+
 def archive_directory(source, dest)
   BigBlueButton.logger.info("Archiving contents of #{source}")
   FileUtils.mkdir_p(dest)
@@ -207,14 +238,14 @@ archive_notes(meeting_id, notes_endpoint, notes_formats, raw_archive_dir)
 # Presentation files
 archive_directory("#{presentation_dir}/#{meeting_id}/#{meeting_id}", "#{target_dir}/presentation")
 # Kurento media
-archive_directory("#{kurento_screenshare_dir}/#{meeting_id}", "#{target_dir}/deskshare")
-archive_directory("#{kurento_video_dir}/#{meeting_id}", "#{target_dir}/video/#{meeting_id}")
+remux_and_archive("#{kurento_screenshare_dir}/#{meeting_id}", "#{target_dir}/deskshare")
+remux_and_archive("#{kurento_video_dir}/#{meeting_id}", "#{target_dir}/video/#{meeting_id}")
 # mediasoup media
 archive_directory("#{mediasoup_screenshare_dir}/#{meeting_id}", "#{target_dir}/deskshare")
 archive_directory("#{mediasoup_video_dir}/#{meeting_id}", "#{target_dir}/video/#{meeting_id}")
 # bbb-webrtc-recorder media
-archive_directory("#{webrtc_recorder_screenshare_dir}/#{meeting_id}", "#{target_dir}/deskshare")
-archive_directory("#{webrtc_recorder_video_dir}/#{meeting_id}", "#{target_dir}/video/#{meeting_id}")
+remux_and_archive("#{webrtc_recorder_screenshare_dir}/#{meeting_id}", "#{target_dir}/deskshare")
+remux_and_archive("#{webrtc_recorder_video_dir}/#{meeting_id}", "#{target_dir}/video/#{meeting_id}")
 
 # If this was the last (or only) segment in a recording, delete the original media files
 if break_timestamp.nil?